ClawHub
Back to skill

Security audit

it-ops-orchestrator

Security checks across malware telemetry and agentic risk

Overview

This is an instruction-only IT operations routing skill with disclosed broad coordination behavior and no executable code or hidden persistence.

Install this if you want help routing IT operations work across specialist agents. Because it can produce guidance for sensitive admin environments, confirm scope, approvals, and rollback plans before applying any generated scripts or infrastructure changes, and avoid sharing secrets unless absolutely necessary.

SkillSpector

By NVIDIA
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The skill is framed as a broad meta-orchestrator with very general routing authority and few explicit invocation boundaries. In an agent system, ambiguous scope can cause over-activation, inappropriate task capture, and unsafe delegation across sensitive IT/security domains, increasing the chance of unintended privileged guidance or execution paths.

Natural-Language Policy Violations

Medium
Confidence
84% confidence
Finding
A PowerShell-first default biases the orchestrator toward a privileged automation path even when safer, simpler, or platform-appropriate alternatives may exist. In IT operations contexts, this can normalize script-based changes on Windows and hybrid environments without explicit user opt-in, raising the risk of unnecessary privilege use, unsafe automation, or policy-incompatible recommendations.

VirusTotal

65/65 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.